diff options
Diffstat (limited to 'hw/acpi/ghes.c')
-rw-r--r-- | hw/acpi/ghes.c | 240 |
1 files changed, 138 insertions, 102 deletions
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index e9511d9..b85bb48 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -28,15 +28,12 @@ #include "hw/nvram/fw_cfg.h" #include "qemu/uuid.h" -#define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" -#define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" +#define ACPI_HW_ERROR_FW_CFG_FILE "etc/hardware_errors" +#define ACPI_HW_ERROR_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" /* The max size in bytes for one error block */ #define ACPI_GHES_MAX_RAW_DATA_LENGTH (1 * KiB) -/* Now only support ARMv8 SEA notification type error source */ -#define ACPI_GHES_ERROR_SOURCE_COUNT 1 - /* Generic Hardware Error Source version 2 */ #define ACPI_GHES_SOURCE_GENERIC_ERROR_V2 10 @@ -184,51 +181,24 @@ static void acpi_ghes_build_append_mem_cper(GArray *table, build_append_int_noprefix(table, 0, 7); } -static int acpi_ghes_record_mem_error(uint64_t error_block_address, - uint64_t error_physical_addr) +static void +ghes_gen_err_data_uncorrectable_recoverable(GArray *block, + const uint8_t *section_type, + int data_length) { - GArray *block; - - /* Memory Error Section Type */ - const uint8_t uefi_cper_mem_sec[] = - UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ - 0xED, 0x7C, 0x83, 0xB1); - /* invalid fru id: ACPI 4.0: 17.3.2.6.1 Generic Error Data, * Table 17-13 Generic Error Data Entry */ QemuUUID fru_id = {}; - uint32_t data_length; - - block = g_array_new(false, true /* clear */, 1); - - /* This is the length if adding a new generic error data entry*/ - data_length = ACPI_GHES_DATA_LENGTH + ACPI_GHES_MEM_CPER_LENGTH; - /* - * It should not run out of the preallocated memory if adding a new generic - * error data entry - */ - assert((data_length + ACPI_GHES_GESB_SIZE) <= - ACPI_GHES_MAX_RAW_DATA_LENGTH); /* Build the new generic error status block header */ acpi_ghes_generic_error_status(block, ACPI_GEBS_UNCORRECTABLE, 0, 0, data_length, ACPI_CPER_SEV_RECOVERABLE); /* Build this new generic error data entry header */ - acpi_ghes_generic_error_data(block, uefi_cper_mem_sec, + acpi_ghes_generic_error_data(block, section_type, ACPI_CPER_SEV_RECOVERABLE, 0, 0, ACPI_GHES_MEM_CPER_LENGTH, fru_id, 0); - - /* Build the memory section CPER for above new generic error data entry */ - acpi_ghes_build_append_mem_cper(block, error_physical_addr); - - /* Write the generic error data entry into guest memory */ - cpu_physical_memory_write(error_block_address, block->data, block->len); - - g_array_free(block, true); - - return 0; } /* @@ -236,7 +206,7 @@ static int acpi_ghes_record_mem_error(uint64_t error_block_address, * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs. * See docs/specs/acpi_hest_ghes.rst for blobs format. */ -void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) +static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) { int i, error_status_block_offset; @@ -264,7 +234,7 @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) ACPI_GHES_MAX_RAW_DATA_LENGTH * ACPI_GHES_ERROR_SOURCE_COUNT); /* Tell guest firmware to place hardware_errors blob into RAM */ - bios_linker_loader_alloc(linker, ACPI_GHES_ERRORS_FW_CFG_FILE, + bios_linker_loader_alloc(linker, ACPI_HW_ERROR_FW_CFG_FILE, hardware_errors, sizeof(uint64_t), false); for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { @@ -273,23 +243,31 @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) * corresponding "Generic Error Status Block" */ bios_linker_loader_add_pointer(linker, - ACPI_GHES_ERRORS_FW_CFG_FILE, sizeof(uint64_t) * i, - sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, - error_status_block_offset + i * ACPI_GHES_MAX_RAW_DATA_LENGTH); + ACPI_HW_ERROR_FW_CFG_FILE, + sizeof(uint64_t) * i, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, + error_status_block_offset + + i * ACPI_GHES_MAX_RAW_DATA_LENGTH); } /* * tell firmware to write hardware_errors GPA into * hardware_errors_addr fw_cfg, once the former has been initialized. */ - bios_linker_loader_write_pointer(linker, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, - 0, sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, 0); + bios_linker_loader_write_pointer(linker, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, 0, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, 0); } /* Build Generic Hardware Error Source version 2 (GHESv2) */ -static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) +static void build_ghes_v2(GArray *table_data, + BIOSLinker *linker, + enum AcpiGhesNotifyType notify, + uint16_t source_id) { uint64_t address_offset; + /* * Type: * Generic Hardware Error Source version 2(GHESv2 - Type 10) @@ -316,21 +294,13 @@ static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 0x40, 0, 4 /* QWord access */, 0); bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, - address_offset + GAS_ADDR_OFFSET, sizeof(uint64_t), - ACPI_GHES_ERRORS_FW_CFG_FILE, source_id * sizeof(uint64_t)); + address_offset + GAS_ADDR_OFFSET, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, + source_id * sizeof(uint64_t)); - switch (source_id) { - case ACPI_HEST_SRC_ID_SEA: - /* - * Notification Structure - * Now only enable ARMv8 SEA notification type - */ - build_ghes_hw_error_notification(table_data, ACPI_GHES_NOTIFY_SEA); - break; - default: - error_report("Not support this error source"); - abort(); - } + /* Notification Structure */ + build_ghes_hw_error_notification(table_data, notify); /* Error Status Block Length */ build_append_int_noprefix(table_data, ACPI_GHES_MAX_RAW_DATA_LENGTH, 4); @@ -344,9 +314,11 @@ static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 0x40, 0, 4 /* QWord access */, 0); bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, - address_offset + GAS_ADDR_OFFSET, - sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, - (ACPI_GHES_ERROR_SOURCE_COUNT + source_id) * sizeof(uint64_t)); + address_offset + GAS_ADDR_OFFSET, + sizeof(uint64_t), + ACPI_HW_ERROR_FW_CFG_FILE, + (ACPI_GHES_ERROR_SOURCE_COUNT + source_id) + * sizeof(uint64_t)); /* * Read Ack Preserve field @@ -359,17 +331,21 @@ static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) } /* Build Hardware Error Source Table */ -void acpi_build_hest(GArray *table_data, BIOSLinker *linker, +void acpi_build_hest(GArray *table_data, GArray *hardware_errors, + BIOSLinker *linker, const char *oem_id, const char *oem_table_id) { AcpiTable table = { .sig = "HEST", .rev = 1, .oem_id = oem_id, .oem_table_id = oem_table_id }; + build_ghes_error_table(hardware_errors, linker); + acpi_table_begin(&table, table_data); /* Error Source Count */ build_append_int_noprefix(table_data, ACPI_GHES_ERROR_SOURCE_COUNT, 4); - build_ghes_v2(table_data, ACPI_HEST_SRC_ID_SEA, linker); + build_ghes_v2(table_data, linker, + ACPI_GHES_NOTIFY_SEA, ACPI_HEST_SRC_ID_SEA); acpi_table_end(linker, &table); } @@ -378,70 +354,130 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s, GArray *hardware_error) { /* Create a read-only fw_cfg file for GHES */ - fw_cfg_add_file(s, ACPI_GHES_ERRORS_FW_CFG_FILE, hardware_error->data, + fw_cfg_add_file(s, ACPI_HW_ERROR_FW_CFG_FILE, hardware_error->data, hardware_error->len); /* Create a read-write fw_cfg file for Address */ - fw_cfg_add_file_callback(s, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, NULL, NULL, - NULL, &(ags->ghes_addr_le), sizeof(ags->ghes_addr_le), false); + fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL, + NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false); ags->present = true; } -int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) +static void get_hw_error_offsets(uint64_t ghes_addr, + uint64_t *cper_addr, + uint64_t *read_ack_register_addr) +{ + if (!ghes_addr) { + return; + } + + /* + * non-HEST version supports only one source, so no need to change + * the start offset based on the source ID. Also, we can't validate + * the source ID, as it is stored inside the HEST table. + */ + + cpu_physical_memory_read(ghes_addr, cper_addr, + sizeof(*cper_addr)); + + *cper_addr = le64_to_cpu(*cper_addr); + + /* + * As the current version supports only one source, the ack offset is + * just sizeof(uint64_t). + */ + *read_ack_register_addr = ghes_addr + sizeof(uint64_t); +} + +static void ghes_record_cper_errors(const void *cper, size_t len, + uint16_t source_id, Error **errp) { - uint64_t error_block_addr, read_ack_register_addr, read_ack_register = 0; - uint64_t start_addr; - bool ret = -1; + uint64_t cper_addr = 0, read_ack_register_addr = 0, read_ack_register; AcpiGedState *acpi_ged_state; AcpiGhesState *ags; - assert(source_id < ACPI_HEST_SRC_ID_RESERVED); + if (len > ACPI_GHES_MAX_RAW_DATA_LENGTH) { + error_setg(errp, "GHES CPER record is too big: %zd", len); + return; + } acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED, NULL)); - g_assert(acpi_ged_state); + if (!acpi_ged_state) { + error_setg(errp, "Can't find ACPI_GED object"); + return; + } ags = &acpi_ged_state->ghes_state; - start_addr = le64_to_cpu(ags->ghes_addr_le); + assert(ACPI_GHES_ERROR_SOURCE_COUNT == 1); + get_hw_error_offsets(le64_to_cpu(ags->hw_error_le), + &cper_addr, &read_ack_register_addr); + + if (!cper_addr) { + error_setg(errp, "can not find Generic Error Status Block"); + return; + } + + cpu_physical_memory_read(read_ack_register_addr, + &read_ack_register, sizeof(read_ack_register)); + + /* zero means OSPM does not acknowledge the error */ + if (!read_ack_register) { + error_setg(errp, + "OSPM does not acknowledge previous error," + " so can not record CPER for current error anymore"); + return; + } + + read_ack_register = cpu_to_le64(0); + /* + * Clear the Read Ack Register, OSPM will write 1 to this register when + * it acknowledges the error. + */ + cpu_physical_memory_write(read_ack_register_addr, + &read_ack_register, sizeof(uint64_t)); + + /* Write the generic error data entry into guest memory */ + cpu_physical_memory_write(cper_addr, cper, len); +} - if (physical_address) { +int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address) +{ + /* Memory Error Section Type */ + const uint8_t guid[] = + UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ + 0xED, 0x7C, 0x83, 0xB1); + Error *errp = NULL; + int data_length; + GArray *block; - if (source_id < ACPI_HEST_SRC_ID_RESERVED) { - start_addr += source_id * sizeof(uint64_t); - } + block = g_array_new(false, true /* clear */, 1); - cpu_physical_memory_read(start_addr, &error_block_addr, - sizeof(error_block_addr)); + data_length = ACPI_GHES_DATA_LENGTH + ACPI_GHES_MEM_CPER_LENGTH; + /* + * It should not run out of the preallocated memory if adding a new generic + * error data entry + */ + assert((data_length + ACPI_GHES_GESB_SIZE) <= + ACPI_GHES_MAX_RAW_DATA_LENGTH); - error_block_addr = le64_to_cpu(error_block_addr); + ghes_gen_err_data_uncorrectable_recoverable(block, guid, data_length); - read_ack_register_addr = start_addr + - ACPI_GHES_ERROR_SOURCE_COUNT * sizeof(uint64_t); + /* Build the memory section CPER for above new generic error data entry */ + acpi_ghes_build_append_mem_cper(block, physical_address); - cpu_physical_memory_read(read_ack_register_addr, - &read_ack_register, sizeof(read_ack_register)); + /* Report the error */ + ghes_record_cper_errors(block->data, block->len, source_id, &errp); - /* zero means OSPM does not acknowledge the error */ - if (!read_ack_register) { - error_report("OSPM does not acknowledge previous error," - " so can not record CPER for current error anymore"); - } else if (error_block_addr) { - read_ack_register = cpu_to_le64(0); - /* - * Clear the Read Ack Register, OSPM will write it to 1 when - * it acknowledges this error. - */ - cpu_physical_memory_write(read_ack_register_addr, - &read_ack_register, sizeof(uint64_t)); + g_array_free(block, true); - ret = acpi_ghes_record_mem_error(error_block_addr, - physical_address); - } else - error_report("can not find Generic Error Status Block"); + if (errp) { + error_report_err(errp); + return -1; } - return ret; + return 0; } bool acpi_ghes_present(void) |